DeepLearning L9
DeepLearning L9
Chuan Li
Lambda Labs
Collaborators: Thu Nguyen-Phuoc, Bing Xu, Yongliang Yang, Stephen Balaban, Lucas Theis, Christian Richardt, Junfei
Zhang, Rui Wang, Kun Xu, Rui Tang
Forward (Computer Graphics)
Model Pictures
Forward (Computer Graphics)
Model Pictures
P1
P0
P1
P0
P1
R
01 |T
01
Inverse (Computer Vision)
P0
P1
R
01 |T
01
Inverse (Computer Vision)
P0
P1 P2
R
01 |T
T 12
01
R 12 |
Building Rome in a Day
Sameer Agarwal, Noah Snavely, Ian Simon, Steven M. Seitz and Richard Szeliski
Sub-module
End-2-End
Model Pictures
Differentiable Rendering
1 SPP
2048 SPP
Sub-modules
Mastering the game of Go with deep neural networks and tree search
David Silver et al.
Sub-modules
Value Network
Mastering the game of Go with deep neural networks and tree search
David Silver et al.
Sub-modules
Policy Network
Value Network
Mastering the game of Go with deep neural networks and tree search
David Silver et al.
Value Networks
Denoising
Policy Networks
Same SPP
Value Networks
Denoising
Policy Networks
Same SPP
4 SPP Denoised 32K SPP Ray Tracing
1 sec 2080 Ti 90 mins 12 cores CPU
Adversarial Monte Carlo denoising with conditioned auxiliary feature modulation
B Xu et al. Siggraph Asia 2019
Input Encoder x Decoder Output
loss
Ref
loss
Specular Specular
Input
Encoder x Decoder
Output
Ref
loss
Specular Specular
Input
Encoder x Decoder
Output
Ref
Auxiliary
Albedo, normal, depth
x
Element-wise
Biasing
Conv
LeakyReLU
Conv
Auxiliary
x
Element-wise Element-wise
Scaling Biasing
Conv Conv
LeakyReLU LeakyReLU
Conv Conv
Auxiliary
x
Element-wise Element-wise
Scaling (AND) Biasing (OR)
Conv Conv
LeakyReLU LeakyReLU
Conv Conv
Auxiliary
Denoise comparison 4 SPP
Policy Networks
Same SPP
Neural Importance Sampling
Thomas Müller et al. ACM Transactions on Graphics 2019
incidence radiance map
Model Pictures
Differentiable Rendering
Ray Tracing Rasterization
Image Centric Object Centric
Visibility
32 x 32 x 32 x 16
32 x 32 x 32 x 16 32 x 32 x 512
32 x 32 x 32 x 16 32 x 32 x 512
32 x 32 x 32 x 16 32 x 32 x 512
Toon
Ambient Occlusion
RenderNet: A deep convolutional network for differentiable rendering from 3D shapes
Thu Nguyen-Phuoc et al. NeurIPS 2018
RenderNet: A deep convolutional network for differentiable rendering from 3D shapes
Thu Nguyen-Phuoc et al. NeurIPS 2018
RenderNet: A deep convolutional network for differentiable rendering from 3D shapes
Thu Nguyen-Phuoc et al. NeurIPS 2018
3D Neural Neural 2D
3D-2D
Encoder Voxels Pixels Decoder
64 x 64 x 64 x 1
Channel-wise Concatenation
Texture Neural
or Texture
Network
Voxels
64 x 64 x 64 x 4
Model Pictures
?
Approximation Target
Approximation Rendered Target
Approximation
Approximation Rendered Target
Approximation
Loss
Back-propagate
Updated Rendered Target
Approximation Approximation
Loss
Back-propagate
Updated Rendered Target
Approximation Approximation
Loss
Back-propagate
For Free
Updated Rendered Target
Approximation Approximation
Expensive
Loss
Back-propagate
Rendered Target
Approximation
Encoder Decoder
Info GANs
3D StyleGAN
3D StyleGAN
3D StyleGAN
Real/Fake
Model Pictures
Model Pictures
Lucas Theis Christian Richardt Junfei Zhang Rui Wang Kun Xu Rui Tang